CoChat
Sign Up
Cited by 20Smart Grid and Power SystemsPower System Optimization and StabilityOptimal Power Flow Distribution

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

GridMind: LLMs-Powered Agents for Power System Analysis and Operations

Open access
Jin, Hongwei, Kim, Kibaek, Kwon, Jonghwan·2025·Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis
DOI 10.1145/3731599.3767409
Open this paper in CoChat — free account

Abstract

The complexity of traditional power system analysis workflows presents significant barriers to efficient decision-making in modern electric grids. This paper presents GridMind, a multi-agent AI system that integrates Large Language Models (LLMs) with deterministic engineering solvers to enable conversational scientific computing for power system analysis. The system employs specialized agents coordinating AC Optimal Power Flow and N-1 contingency analysis through natural language interfaces while maintaining numerical precision via function calls. GridMind addresses workflow integration, knowledge accessibility, context preservation, and expert decision-support augmentation. Experimental evaluation on IEEE test cases demonstrates that the proposed agentic framework consistently delivers correct solutions across all tested language models, with smaller LLMs achieving comparable analytical accuracy with reduced computational latency. This work establishes agentic AI as a viable paradigm for scientific computing, demonstrating how conversational interfaces can enhance accessibility while preserving numerical rigor essential for critical engineering applications.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1145/3731599.3767409

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 : Figure 1: GridMind: LLM Agents for Powewr System
Figure 1 : Figure 1: GridMind: LLM Agents for Powewr SystemCC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 25

  1. MA Abido. 2002. Optimal power flow using particle swarm optimization. International Journal of Electrical Power & Energy Systems 24 7 (2002) 563–571. · DOI
  2. Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877–1901.
  3. Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde De Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:https://arXiv.org/abs/2107.03374 (2021). · arXiv
  4. 10.23919/PSCC.2018.8442948 · DOI
  5. Yangruibo Ding Zijian Wang Wasi Ahmad Hantian Ding Ming Tan Nihal Jain Murali Krishna Ramanathan Ramesh Nallapati Parminder Bhatia Dan Roth et al. 2023. Crosscodeeval: A diverse and multilingual benchmark for cross-file code completion. Advances in Neural Information Processing Systems 36 (2023) 46701–46723. · DOI
  6. Ian Dobson Benjamin A Carreras Vickie E Lynch and David E Newman. 2007. Complex systems analysis of series of blackouts: Cascading failure critical points and self-organization. Chaos: An Interdisciplinary Journal of Nonlinear Science 17 2 (2007). · DOI
  7. GC Ejebe and BF Wollenberg. 2007. Automatic contingency selection. IEEE transactions on Power Apparatus and Systems1 (2007) 97–109. · DOI
  8. Shanshan Han Qifan Zhang Yuhang Yao Weizhao Jin and Zhaozhuo Xu. 2024. LLM multi-agent systems: Challenges and open problems. arXiv preprint arXiv:https://arXiv.org/abs/2402.03578 (2024). · arXiv
  9. M Huneault and Francisco D Galiana. 2002. A survey of the optimal power flow literature. IEEE transactions on Power Systems 6 2 (2002) 762–770. · DOI
  10. Javad Lavaei and Steven H Low. 2011. Zero duality gap in optimal power flow problem. IEEE Transactions on Power systems 27 1 (2011) 92–107. · DOI
  11. Raymond Li Loubna Ben Allal Yangtian Zi Niklas Muennighoff Denis Kocetkov Chenghao Mou Marc Marone Christopher Akiki Jia Li Jenny Chim et al. 2023. Starcoder: may the source be with you! arXiv preprint arXiv:https://arXiv.org/abs/2305.06161 (2023). · arXiv
  12. Xingpeng Li Pranavamoorthy Balasubramanian Mostafa Sahraei-Ardakani Mojdeh Abdi-Khorsand Kory W Hedman and Robin Podmore. 2016. Real-time contingency analysis with corrective transmission switching. IEEE Transactions on Power Systems 32 4 (2016) 2604–2617. · DOI
  13. Xiao Liu Hao Yu Hanchen Zhang Yifan Xu Xuanyu Lei Hanyu Lai Yu Gu Hangliang Ding Kaiwen Men Kejuan Yang et al. 2023. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:https://arXiv.org/abs/2308.03688 (2023). · arXiv
  14. Erik Nijkamp Bo Pang Hiroaki Hayashi Lifu Tu Huan Wang Yingbo Zhou Silvio Savarese and Caiming Xiong. 2022. Codegen: An open large language model for code with multi-turn program synthesis. arXiv preprint arXiv:https://arXiv.org/abs/2203.13474 (2022). · arXiv
  15. OpenAI. 2023. GPT-4 technical report. arXiv preprint arXiv:https://arXiv.org/abs/2303.08774 (2023). · arXiv
  16. Giuliano Andrea Pagani and Marco Aiello. 2013. The power grid as a complex network: a survey. Physica A: Statistical Mechanics and its Applications 392 11 (2013) 2688–2700. · DOI
  17. Mania Pavella, Damien Ernst, and Daniel Ruiz-Vega. 2012. Transient stability of power systems: a unified approach to assessment and control. Springer Science & Business Media.
  18. Victor H Quintana Geraldo L Torres and Jose Medina-Palomo. 2000. Interior-point methods and their applications to power systems: a classification of publications and software codes. IEEE Transactions on power systems 15 1 (2000) 170–176. · DOI
  19. Mostafa Sahraei-Ardakani Xingpeng Li P Balasubramanian KW Hedman and Mojdeh Abdi-Khorsand. 2015. Real-time contingency analysis with transmission switching on real power system data. IEEE Transactions on Power Systems 31 3 (2015) 2501–2502. · DOI
  20. Samuel Schmidgall Yusheng Su Ze Wang Ximeng Sun Jialian Wu Xiaodong Yu Jiang Liu Michael Moor Zicheng Liu and Emad Barsoum. 2025. Agent laboratory: Using llm agents as research assistants. arXiv preprint arXiv:https://arXiv.org/abs/2501.04227 (2025). · DOI · Paper page
  21. Leon Thurner Alexander Scheidler Florian Schäfer Jan-Hendrik Menke Julian Dollichon Friederike Meier Steffen Meinecke and Martin Braun. 2018. pandapower—an open-source python tool for convenient modeling analysis and optimization of electric power systems. IEEE Transactions on Power Systems 33 6 (2018) 6510–6521. · DOI
  22. 10.5555/1695886 · DOI
  23. Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Shaokun Zhang Erkang Zhu Beibin Li Li Jiang Xiaoyun Zhang and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:https://arXiv.org/abs/2308.08155 3 4 (2023). · arXiv
  24. Xuan Wu and Antonio J Conejo. 2019. Security-constrained ACOPF: Incorporating worst contingencies and discrete controllers. IEEE Transactions on Power Systems 35 3 (2019) 1936–1945. · DOI
  25. Ray Daniel Zimmerman Carlos Edmundo Murillo-Sánchez and Robert John Thomas. 2010. MATPOWER: Steady-state operations planning and analysis tools for power systems research and education. IEEE Transactions on power systems 26 1 (2010) 12–19. · DOI

Cited by

Sorted by citations

See all 20

Metadata

Authors
Jin, H., Kim, K., & Kwon, J.
Affiliations
Argonne National Laboratory (US)
ORCID
Venue
Proceedings of the SC '25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis
Publisher
ACM
Published
2025-11-15
Pages
560-568
ISSN
2167-4337 (ISSN-L)
DOI
10.1145/3731599.3767409
OpenAlex
W4416003928
Cited by
20
References
1
Citations by year
2026: 19 · 2025: 1
FWCI
35.44
Type
conference paper
Language
en
Open access
Licence
cc-by
Locations
  • International Conference for High Performance Computing, Networking, Storage and Analysis (SC) (publishedVersion, cc-by)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • U.S. Department of Energy (DE‐ AC02‐06CH11357, AC02‐06CH11357)
  • Office of Science (AC02‐06CH11357, DE-AC02, 06CH11357, DE-AC02-06CH11357)
  • Laboratory Directed Research and Development (DE‐AC02‐06CH11357)
  • Argonne National Laboratory (DE- AC02-06-CH11357, DE-AC02, AC02–06CH11357, 06CH11357)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Smart Grid and Power Systems
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Power System Optimization and Stability
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Optimal Power Flow Distribution
Keywords
multi-agent systems, large language models, power system analysis, optimal power flow, N-1 contingency analysis, natural language interfaces, LLM agents, power system operation, decision support

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review